CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation

TL;DR

CritiFusion is an inference-time framework that enhances text-to-image diffusion models by integrating semantic critique and spectral refinement, significantly improving alignment, detail, and realism without additional training.

Contribution

We introduce CritiFusion, a novel plug-in method combining semantic critique and spectral alignment to improve text-to-image generation fidelity and detail without retraining models.

Findings

Improves human-aligned metrics of text-image correspondence

Enhances visual quality and realism of generated images

Achieves state-of-the-art performance on benchmark evaluations

Abstract

Recent text-to-image diffusion models have achieved remarkable visual fidelity but often struggle with semantic alignment to complex prompts. We introduce CritiFusion, a novel inference-time framework that integrates a multimodal semantic critique mechanism with frequency-domain refinement to improve text-to-image consistency and detail. The proposed CritiCore module leverages a vision-language model and multiple large language models to enrich the prompt context and produce high-level semantic feedback, guiding the diffusion process to better align generated content with the prompt's intent. Additionally, SpecFusion merges intermediate generation states in the spectral domain, injecting coarse structural information while preserving high-frequency details. No additional model training is required. CritiFusion serves as a plug-in refinement stage compatible with existing diffusion backbones. Experiments on standard benchmarks show that our method notably improves human-aligned metrics of text-to-image correspondence and visual quality. CritiFusion consistently boosts performance on human preference scores and aesthetic evaluations, achieving results on par with state-of-the-art reward optimization approaches. Qualitative results further demonstrate superior detail, realism, and prompt fidelity, indicating the effectiveness of our semantic critique and spectral alignment strategy.